{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T23:32:54Z","timestamp":1774999974362,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1009938","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2022,8,31]],"date-time":"2022-08-31T00:00:00Z","timestamp":1661904000000}}],"reference-count":43,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2022,8,19]],"date-time":"2022-08-19T00:00:00Z","timestamp":1660867200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100001642","name":"Glenn Foundation for Medical Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100001642","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["K99 AG070102"],"award-info":[{"award-number":["K99 AG070102"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["F32 AG069363"],"award-info":[{"award-number":["F32 AG069363"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NIDDK Mouse Metabolic Phenotyping Centers","award":["DK076169"],"award-info":[{"award-number":["DK076169"]}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["T32AG023480"],"award-info":[{"award-number":["T32AG023480"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Epigenetic clocks allow us to accurately predict the age and future health of individuals based on the methylation status of specific CpG sites in the genome and are a powerful tool to measure the effectiveness of longevity interventions. There is a growing need for methods to efficiently construct epigenetic clocks. The most common approach is to create clocks using elastic net regression modelling of all measured CpG sites, without first identifying specific features or CpGs of interest. The addition of feature selection approaches provides the opportunity to optimise the identification of predictive CpG sites. Here, we apply novel feature selection methods and combinatorial approaches including newly adapted neural networks, genetic algorithms, and \u2018chained\u2019 combinations. Human whole blood methylation data of ~470,000 CpGs was used to develop clocks that predict age with R2 correlation scores of greater than 0.73, the most predictive of which uses 35 CpG sites for a R2 correlation score of 0.87. The five most frequent sites across all clocks were modelled to build a clock with a R2 correlation score of 0.83. These two clocks are validated on two external datasets where they maintain excellent predictive accuracy. When compared with three published epigenetic clocks (Hannum, Horvath, Weidner) also applied to these validation datasets, our clocks outperformed all three models. We identified gene regulatory regions associated with selected CpGs as possible targets for future aging studies. Thus, our feature selection algorithms build accurate, generalizable clocks with a low number of CpG sites, providing important tools for the field.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1009938","type":"journal-article","created":{"date-parts":[[2022,8,19]],"date-time":"2022-08-19T13:47:21Z","timestamp":1660916841000},"page":"e1009938","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":14,"title":["Novel feature selection methods for construction of accurate epigenetic clocks"],"prefix":"10.1371","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5075-5194","authenticated-orcid":true,"given":"Adam","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2842-1072","authenticated-orcid":true,"given":"Amber","family":"Mueller","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5957-3063","authenticated-orcid":true,"given":"Brad","family":"English","sequence":"additional","affiliation":[]},{"given":"Anthony","family":"Arena","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2202-7397","authenticated-orcid":true,"given":"Daniel","family":"Vera","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4303-0491","authenticated-orcid":true,"given":"Alice E.","family":"Kane","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9936-436X","authenticated-orcid":true,"given":"David A.","family":"Sinclair","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2022,8,19]]},"reference":[{"issue":"6","key":"pcbi.1009938.ref001","doi-asserted-by":"crossref","first-page":"e14821","DOI":"10.1371\/journal.pone.0014821","article-title":"Epigenetic predictor of age","volume":"6","author":"S Bocklandt","year":"2011","journal-title":"PLoS One"},{"issue":"10","key":"pcbi.1009938.ref002","doi-asserted-by":"crossref","first-page":"R115","DOI":"10.1186\/gb-2013-14-10-r115","article-title":"DNA methylation age of human tissues and cell types","volume":"14","author":"S Horvath","year":"2013","journal-title":"Genome Biology"},{"issue":"1","key":"pcbi.1009938.ref003","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1038\/npp.2012.112","article-title":"DNA Methylation and Its Basic Function","volume":"38","author":"L Moore","year":"2013","journal-title":"Neuropsychopharmacology"},{"issue":"10","key":"pcbi.1009938.ref004","doi-asserted-by":"crossref","first-page":"2832","DOI":"10.18632\/aging.101590","article-title":"A multi-tissue full lifespan epigenetic clock for mice","volume":"10","author":"M Thompson","year":"2018","journal-title":"Aging"},{"issue":"2","key":"pcbi.1009938.ref005","doi-asserted-by":"crossref","first-page":"303","DOI":"10.18632\/aging.101684","article-title":"DNA methylation GrimAge strongly predicts lifespan and healthspan","volume":"11","author":"A Lu","year":"2019","journal-title":"Aging"},{"issue":"2","key":"pcbi.1009938.ref006","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/j.molcel.2012.10.016","article-title":"Genome-wide Methylation Profiles Reveal Quantitative Views of Human Aging Rates","volume":"49","author":"G Hannum","year":"2013","journal-title":"Molecular Cell"},{"issue":"1","key":"pcbi.1009938.ref007","article-title":"Estimation of chimpanzee age based on DNA methylation","volume":"8","author":"H Ito","year":"2018","journal-title":"Scientific Reports"},{"key":"pcbi.1009938.ref008","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.fsigen.2016.03.005","article-title":"Identification and evaluation of age-correlated DNA methylation markers for forensic use","volume":"23","author":"JL Park","year":"2016","journal-title":"Forensic Sci Int Genet"},{"issue":"1","key":"pcbi.1009938.ref009","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00414-017-1636-0","article-title":"DNA methylation in ELOVL2 and C1orf132 correctly predicted chronological age of individuals from three disease groups","volume":"132","author":"M Sp\u00f3lnicka","year":"2017","journal-title":"International Journal of Legal Medicine"},{"issue":"2014","key":"pcbi.1009938.ref010","first-page":"161","article-title":"Examination of DNA methylation status of the ELOVL2 marker may be useful for human age prediction in forensic science","volume":"14","author":"R Zbie\u0107-Piekarska","year":"2014","journal-title":"Forensic Science International: Genetics"},{"key":"pcbi.1009938.ref011","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.fsigen.2017.07.011","article-title":"Detection and evaluation of DNA methylation markers found at SCGN and KLF14 loci to estimate human age","volume":"31","author":"H Alghanim","year":"2017","journal-title":"Forensic Science International: Genetics"},{"issue":"2","key":"pcbi.1009938.ref012","doi-asserted-by":"crossref","first-page":"R24","DOI":"10.1186\/gb-2014-15-2-r24","article-title":"Aging of blood can be tracked by DNA methylation changes at just three CpG sites","volume":"15","author":"CI Weidner","year":"2014","journal-title":"Genome Biology"},{"key":"pcbi.1009938.ref013","first-page":"1157","article-title":"An Introduction to Variable and Feature Selection","volume":"3","author":"I Guyon","year":"2003","journal-title":"Journal of Machine Learning Research"},{"issue":"12","key":"pcbi.1009938.ref014","doi-asserted-by":"crossref","first-page":"r137","DOI":"10.1186\/gb-2013-14-12-r137","article-title":"Integrative DNA methylation and gene expression analysis in high-grade soft tissue sarcomas","volume":"14","author":"M Renner","year":"2013","journal-title":"Genome Biology"},{"issue":"S1","key":"pcbi.1009938.ref015","doi-asserted-by":"crossref","DOI":"10.1186\/s12863-018-0633-8","article-title":"Using recursive feature elimination in random forest to account for correlated variables in high dimensional data","volume":"19","author":"B Darst","year":"2018","journal-title":"BMC Genetics"},{"issue":"1","key":"pcbi.1009938.ref016","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1186\/1471-2105-9-457","article-title":"Identification of a small optimal subset of CpG sites as bio-markers from high-throughput DNA methylation profiles","volume":"9","author":"H Meng","year":"2008","journal-title":"BMC Bioinformatics"},{"key":"pcbi.1009938.ref017","doi-asserted-by":"crossref","first-page":"349","DOI":"10.3389\/fgene.2019.00349","article-title":"Prognostic and Predictive Value of Three DNA Methylation Signatures in Lung Adenocarcinoma","volume":"10","author":"Y Wang","year":"2019","journal-title":"Front Genet"},{"issue":"2","key":"pcbi.1009938.ref018","doi-asserted-by":"crossref","first-page":"623","DOI":"10.18632\/aging.203847","article-title":"A catalogue of omics biological ageing clocks reveals substantial commonality and associations with disease risk","volume":"14","author":"E Macdonald-Dunlop","year":"2022","journal-title":"Aging"},{"key":"pcbi.1009938.ref019","first-page":"1","author":"A Trapp","year":"2021","journal-title":"Gladyshev VN Profiling epigenetic age in single cells, Nature Aging"},{"key":"pcbi.1009938.ref020","author":"PT Griffin","year":"2021","journal-title":"Ultra-cheap and scalable epigenetic age predictions with TIME-Seq, bioRxiv: 10.1101\/2021.10.25.465725 [Preprint]"},{"issue":"1","key":"pcbi.1009938.ref021","doi-asserted-by":"crossref","first-page":"177","DOI":"10.2217\/epi.09.14","article-title":"Genome-wide DNA methylation profiling using Infinium assay","volume":"1","author":"M Bibikova","year":"2009","journal-title":"Epigenomics"},{"issue":"3","key":"pcbi.1009938.ref022","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1111\/acel.12325","article-title":"Accelerated epigenetic aging in Down syndrome","volume":"14","author":"S Horvath","year":"2015","journal-title":"Aging Cell"},{"issue":"38","key":"pcbi.1009938.ref023","doi-asserted-by":"crossref","first-page":"23329","DOI":"10.1073\/pnas.1820843116","article-title":"The PedBE clock accurately estimates DNA methylation age in pediatric buccal cells","volume":"117","author":"O McEwen L","year":"2019","journal-title":"Proceedings Of The National Academy Of Sciences"},{"key":"pcbi.1009938.ref024","author":"CR Martens","year":"2020","journal-title":"GSE85311 Epigenetic patterns with aging and exercise are associated with indicators of healthspan in humans"},{"issue":"10","key":"pcbi.1009938.ref025","article-title":"Underlying features of epigenetic aging clocks in vivo and in vitro","volume":"19","author":"Z Liu","year":"2020","journal-title":"Aging Cell"},{"issue":"5","key":"pcbi.1009938.ref026","doi-asserted-by":"crossref","first-page":"8091","DOI":"10.1007\/s11042-020-10139-6","article-title":"A review on genetic algorithm: past, present, and future","volume":"80","author":"S Katoch","year":"2020","journal-title":"Multimedia Tools and Applications"},{"key":"pcbi.1009938.ref027","author":"Mathgene.usc.es","year":"2021","journal-title":"Age prediction with DNA methylation: blood, 7 CpGs, EpiTYPER"},{"key":"pcbi.1009938.ref028","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/j.fsigen.2015.05.001","article-title":"Development of a forensically useful age prediction method based on DNA methylation analysis","volume":"17","author":"R Zbie\u0107-Piekarska","year":"2015","journal-title":"Forensic Science International: Genetics"},{"issue":"2","key":"pcbi.1009938.ref029","doi-asserted-by":"crossref","first-page":"e13100","DOI":"10.1111\/acel.13100","article-title":"The lipid elongation enzyme ELOVL2 is a molecular regulator of aging in the retina","volume":"19","author":"D Chen","year":"2020","journal-title":"Aging Cell"},{"issue":"1","key":"pcbi.1009938.ref030","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-018-03649-3","article-title":"CCDC102B confers risk of low vision and blindness in high myopia","volume":"9","author":"Y Hosoda","year":"2018","journal-title":"Nature Communications"},{"issue":"23","key":"pcbi.1009938.ref031","doi-asserted-by":"crossref","first-page":"jcs222901","DOI":"10.1242\/jcs.222901","article-title":"CCDC102B functions in centrosome linker assembly and centrosome cohesion","volume":"131","author":"Y Xia","year":"2018","journal-title":"Journal of Cell Science"},{"key":"pcbi.1009938.ref032","doi-asserted-by":"crossref","first-page":"102189","DOI":"10.1016\/j.fsigen.2019.102189","article-title":"Novel multiplex strategy for DNA methylation-based age prediction from small amounts of DNA via Pyrosequencing","volume":"44","author":"J Fleckhaus","year":"2020","journal-title":"Forensic Science International: Genetics"},{"issue":"11","key":"pcbi.1009938.ref033","doi-asserted-by":"crossref","first-page":"2051","DOI":"10.1093\/gerona\/glaa052","article-title":"Blood DNA Methylation and Aging: A Cross-Sectional Analysis and Longitudinal Validation in the InCHIANTI Study","volume":"75","author":"R Tharakan","year":"2020","journal-title":"The Journals of Gerontology: Series A"},{"issue":"2","key":"pcbi.1009938.ref034","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1016\/j.ajhg.2018.01.005","article-title":"Otud7a Knockout Mice Recapitulate Many Neurological Features of 15q13.3 Microdeletion Syndrome","volume":"102","author":"J Yin","year":"2018","journal-title":"The American Journal of Human Genetics"},{"key":"pcbi.1009938.ref035","doi-asserted-by":"crossref","DOI":"10.3389\/fgene.2021.632620","article-title":"Comparison of Methods for Feature Selection in Clustering of High-Dimensional RNA-Sequencing Data to Identify Cancer Subtypes","volume":"12","author":"D K\u00e4llberg","year":"2021","journal-title":"Frontiers in Genetics"},{"key":"pcbi.1009938.ref036","doi-asserted-by":"crossref","DOI":"10.3389\/fgene.2019.00452","article-title":"Large-Scale Automatic Feature Selection for Biomarker Discovery in High-Dimensional OMICs Data","volume":"10","author":"M Leclercq","year":"2019","journal-title":"Frontiers in Genetics"},{"key":"pcbi.1009938.ref037","first-page":"11","article-title":"Transcriptome profiling by combined machine learning and statistical R analysis identifies TMEM236 as a potential novel diagnostic biomarker for colorectal cancer","author":"N Maurya","year":"2021","journal-title":"Scientific Reports"},{"key":"pcbi.1009938.ref038","article-title":"An Ensemble Feature Selection Method for Biomarker Discovery","author":"A Shahrjooihaghighi","year":"2017","journal-title":"Proc IEEE Int Symp Signal Proc Inf Tech"},{"key":"pcbi.1009938.ref039","doi-asserted-by":"crossref","first-page":"100083","DOI":"10.1016\/j.mcpro.2021.100083","article-title":"Feature Selection Methods for Protein Biomarker Discovery from Proteomics or Multiomics Data","volume":"20","author":"Z Shi","year":"2021","journal-title":"Molecular & Cellular Proteomics"},{"key":"pcbi.1009938.ref040","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2021.645998","article-title":"Identification of Diagnostic Markers for Major Depressive Disorder Using Machine Learning Methods","volume":"15","author":"S Zhao","year":"2021","journal-title":"Frontiers in Neuroscience"},{"key":"pcbi.1009938.ref041","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"JMLR"},{"issue":"11","key":"pcbi.1009938.ref042","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v036.i11","article-title":"Rudnicki WR Feature Selection with the Boruta Package","volume":"36","author":"MB Kursa","year":"2010","journal-title":"Journal of Statistical Software"},{"issue":"2","key":"pcbi.1009938.ref043","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net","volume":"67","author":"H Zou","year":"2005","journal-title":"Journal of the Royal Statistical Society: Series B Statistical Methodology"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1009938","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2022,8,31]],"date-time":"2022-08-31T00:00:00Z","timestamp":1661904000000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1009938","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,31]],"date-time":"2022-08-31T13:44:06Z","timestamp":1661953446000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1009938"}},"subtitle":[],"editor":[{"given":"Chongzhi","family":"Zang","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2022,8,19]]},"references-count":43,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2022,8,19]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1009938","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2022.02.21.481326","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,19]]}}}